Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

naive nn visualisation #331

Open
silky opened this Issue Mar 15, 2018 · 2 comments

Comments

Projects
None yet
2 participants
@silky
Copy link
Owner

silky commented Mar 15, 2018

just reshape all the weights to be in the shape of an image, normalise the values, and output it.

@dcousens

This comment has been minimized.

Copy link

dcousens commented Mar 15, 2018

What do you mean by re-shape?

And is this like, a generic tool?
Would that require a generic output standard?
I'd be interested in this, as in my own visualizations I often don't have the time to write-up a custom solution for the language I am using.

But it would be great to have more-generically on my CLI to pipe it out for quick visualization.

@silky

This comment has been minimized.

Copy link
Owner Author

silky commented Mar 19, 2018

nah it wouldn't be generic

i literally just meant take an array that's say (100, 300) and then reshape it to (100, 100, 3) then plot it.

i did this with some simple model, and it looked kind of interesting at some layers. it kind of tells you something about how many parameters you're using.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.